© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59437
    Prev
    Next
    INDEX
    Explanations

    ICD codes and diagnostic classifications

    np_acts-logits-general · gemini-2.5-flash-lite

    references to medical classification systems, particularly the International Classification of Diseases (ICD-10).

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is specialized in spotting numerical tokens (including standalone numbers and numeric codes).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Garda
    -0.75
    綺麗
    -0.72
     comparative
    -0.72
    edd
    -0.72
     logam
    -0.71
    manız
    -0.70
    pnt
    -0.70
    xss
    -0.69
    zeczytaj
    -0.69
     khuy
    -0.69
    POSITIVE LOGITS
     ICD
    1.60
    ICD
    1.34
     codes
    1.29
    codes
    1.10
     coding
    1.09
     coded
    1.00
     códigos
    0.98
     diagnosis
    0.96
    coded
    0.95
     morbidity
    0.95
    Activations Density 0.072%

    No Known Activations